Medical insurance management mechanism management system and method based on big data

Abstract

The invention discloses a big data-based medical insurance management mechanism management system and method, and relates to the technical field of medical insurance management mechanism management, and the method comprises the steps: analyzing the verification abnormal degree of a medical insurance drug in a drug verification process, and obtaining a feature medical insurance drug; acquiring historical drug sales data of the historical abnormal medical insurance drugs, acquiring drug sales data of the feature medical insurance drugs in the current period, and analyzing drug sales approximation between the feature medical insurance drugs and the historical abnormal medical insurance drugs to obtain target historical abnormal medical insurance drugs; acquiring historical abnormal data of the target historical abnormal medical insurance drugs, and based on the special historical abnormal data, evaluating abnormalities of the characteristic medical insurance drugs in the current period in different sales links in the sales process; and obtaining target abnormal data of the feature medical insurance drugs in the current period, and based on the target abnormal data, performing intelligent management on sales of the medical insurance drugs by a medical insurance management mechanism.

Description

Technical Field

[0001] The present invention relates to the technical field of medical insurance management agency management, and in particular to a medical insurance management agency management system and method based on big data. Background Art

[0002] The amount of data that medical insurance management agencies need to process is very large, covering the insurance information of millions or even hundreds of millions of people, medical records, expense reimbursement, drug use and other data. These large amounts of complex data require big data technology to be gradually applied to the management of medical insurance management agencies. Big data technology can provide a large amount of real-time data and data analysis tools to help medical insurance management agencies make decisions quickly and accurately, thereby improving management efficiency. In addition, big data technology can assist medical insurance management agencies in analyzing abnormal patterns and fraudulent behaviors in the medical insurance process, so as to take appropriate measures to manage and protect the security of medical insurance funds.

[0003] At present, one of the main tasks of the medical insurance management agency is to analyze the sales process of medical insurance drugs. According to the verification results, the medical insurance management agency will investigate and punish the illegal and legal behaviors in the sales process of medical insurance drugs to ensure the authenticity of medical insurance drug transactions. However, the current analysis of anomalies in the sales transaction process of medical insurance drugs mainly relies on regular audits and surprise inspections. This method not only requires a lot of manpower and material resources, which increases management costs, but also requires the support of a large number of professionals to analyze the data in the sales process of medical insurance drugs, which is likely to lead to insufficient resources. In addition, after the traditional method obtains the anomalies in the sales process of medical insurance drugs, it is also difficult to optimize the sales process of medical insurance drugs accordingly. Summary of the invention

[0004] The purpose of the present invention is to provide a medical insurance management agency management system and method based on big data to solve the problems raised in the prior art.

[0005] To achieve the above object, the present invention provides the following technical solution: a management method for a medical insurance management agency based on big data, the method comprising:

[0006] Step S100: Obtaining drug reimbursement data of medical insurance drugs in the current period, analyzing the degree of abnormal reimbursement of medical insurance drugs during the drug reimbursement process, and obtaining characteristic medical insurance drugs;

[0007] Step S200: Obtain historical drug sales data of historical abnormal medical insurance drugs, obtain drug sales data of characteristic medical insurance drugs in the current period, analyze the drug sales similarity between characteristic medical insurance drugs and historical abnormal medical insurance drugs, and obtain target historical abnormal medical insurance drugs;

[0008] Step S300: Obtain historical abnormal data of target historical abnormal medical insurance drugs, and based on the historical abnormal data, evaluate the abnormality of different sales links of characteristic medical insurance drugs in the current cycle during the sales process to obtain target abnormal data;

[0009] Step S400: Acquire target abnormal data of characteristic medical insurance drugs in the current cycle, and based on the target abnormal data, the medical insurance management agency performs intelligent management on the sales of medical insurance drugs.

[0010] Furthermore, step S100 includes:

[0011] Step S101: Obtaining drug reimbursement data of medical insurance drugs sold in the current period from the medical insurance management agency, the drug reimbursement data including the drug code and reimbursement amount of the medical insurance drugs;

[0012] Step S102: according to the drug codes of the medical insurance drugs, the medical insurance drugs with the same drug name and manufacturer are collected to obtain a medical insurance drug set;

[0013] Step S103: Obtain the write-off amount of each medical insurance drug in the medical insurance drug set, and calculate the characteristic data fluctuation value Q of the medical insurance drug set:

[0014]

[0015] Among them, X i is the write-off amount of the ith medical insurance drug in the medical insurance drug set; N is the total number of medical insurance drugs in the medical insurance drug set; μ is the average write-off amount of the medical insurance drugs in the medical insurance drug set;

[0016] Step S104: Calculate the characteristic write-off abnormal value of each medical insurance drug in the medical insurance drug set, where the characteristic write-off abnormal value L of the a-th medical insurance drug in the medical insurance drug set is a :

[0017]

[0018] Among them, X a is the write-off amount of the ath medical insurance drug in the medical insurance drug set;

[0019] Step S105: When the characteristic write-off abnormality value of the ath medical insurance drug is greater than the preset characteristic write-off abnormality threshold, it is determined that the ath medical insurance drug is a drug write-off abnormality in the drug write-off process, and the ath medical insurance drug is recorded as a characteristic medical insurance drug.

[0020] Further, step S200 includes:

[0021] Step S201: Acquire historical drug sales data of historical abnormal medical insurance drugs from a database of a medical insurance management agency, wherein the historical abnormal medical insurance drugs are of the same drug type as the characteristic medical insurance drugs, and the historical drug sales data include data corresponding to various drug sales parameters of the historical abnormal medical insurance drugs;

[0022] Step S202: Obtain drug sales data of characteristic medical insurance drugs, where the drug sales data includes data corresponding to various drug sales parameters of the characteristic medical insurance drugs;

[0023] Step S203: Randomly select a number of historically abnormal medical insurance drugs, perform preprocessing and feature encoding on the various drug sales parameters of the several historically abnormal medical insurance drugs, obtain the feature values ​​of the various drug sales parameters, and construct a data matrix U:

[0024]

[0025] Among them, u jp is the characteristic value of the pth drug sales parameter of the jth historical abnormal medical insurance drug among several historical abnormal medical insurance drugs; u jp is the characteristic value of the pth drug sales parameter of the jth historical abnormal medical insurance drug among several historical abnormal medical insurance drugs; U 1p is the characteristic value of the pth drug sales parameter of the first historical abnormal medical insurance drug among several historical abnormal medical insurance drugs; u j1 is the characteristic value of the first drug sales parameter of the jth historical abnormal medical insurance drug among several historical abnormal medical insurance drugs; j is the total number of several historical abnormal medical insurance drugs; p is the total number of various drug sales parameters;

[0026] Step S204: Standardize each element of the data matrix U to obtain a normalized data matrix U′, and calculate the characteristic covariance matrix C of the data matrix U′:

[0027]

[0028] Among them, U′ T is the transpose of the data matrix U′;

[0029] Step S205: Calculate the eigenvalues ​​λ and eigenvectors v of the eigencovariance matrix C, where the eigenvalues ​​λ and the eigenvectors v satisfy the equation: Cv=λv, where (C-λI)v=0, and sort the eigenvalues ​​in descending order according to their numerical values, and select the eigenvectors corresponding to the preset k eigenvalues ​​to form the projection matrix W;

[0030] Step S206: Based on the drug sales data, preprocess the data corresponding to each drug sales parameter of the characteristic medical insurance drug, and feature encode each drug sales parameter of the preprocessed characteristic medical insurance drug to obtain a characteristic sales vector group F of the characteristic medical insurance drug, and use the projection matrix to reduce the dimension of the characteristic sales vector group F to obtain the main characteristic sales vector group F of the characteristic medical insurance drug △ , where F △ =FW;

[0031] Step S207: Obtain the main characteristic sales vector group of historical abnormal medical insurance drugs, and calculate the drug sales approximation K between the characteristic medical insurance drugs and the g-th historical abnormal medical insurance drug in the database g :

[0032]

[0033] Among them, B g It is represented as the main feature sales vector group of the g-th historical abnormal medical insurance drug;

[0034] Step S208: When the drug sales approximation K g If the drug sales value is greater than the preset drug sales approximation threshold, it is determined that the drug sales status between the characteristic medical insurance drug and the g-th historical abnormal medical insurance drug is similar, and the g-th historical abnormal medical insurance drug is recorded as the target historical abnormal medical insurance drug of the characteristic medical insurance drug;

[0035] The purpose of standardizing each element in the data matrix in the above steps is to eliminate the impact of dimensions between different drug sales parameters of different historical abnormal medical insurance drugs, thereby ensuring the accuracy of the data.

[0036] Furthermore, step S300 includes:

[0037] Step S301: Acquire historical abnormal data of each target historical abnormal medical insurance drug of the characteristic medical insurance drug, where the historical abnormal data is the sales link at which the target historical abnormal medical insurance drug is detected to be abnormal;

[0038] Step S302: Calculate the abnormal value of each sales link in the characteristic medical insurance drug, where the abnormal value H of the sales link of the βth item in the characteristic medical insurance drug is β :

[0039]

[0040] Among them, M sum M is the total number of historical abnormal medical insurance drugs for each target characteristic medical insurance drug; β It is represented by the total number of target historical abnormal medical insurance drugs that are detected to be abnormal in the β-th sales link;

[0041] Step S303: When the abnormal value of the β-th sales link is greater than the preset environmental abnormality threshold, it is determined that the β-th sales link in the characteristic medical insurance drug is abnormal, and the β-th sales link is recorded as the target abnormal sales link in the sales process of the characteristic medical insurance drug;

[0042] Step S304: Gather target abnormal sales links of several items of characteristic medical insurance drugs to obtain target abnormal data of characteristic medical insurance drugs.

[0043] Furthermore, step S400 includes:

[0044] Step S401: Acquire each characteristic medical insurance drug in the current cycle, acquire target abnormal data of each characteristic medical insurance drug, and extract target abnormal sales links of the characteristic medical insurance drug from the target abnormal data;

[0045] Step S402: Based on the target abnormal sales links of each characteristic medical insurance drug in the current cycle, the medical insurance management agency in the current cycle conducts a traceability inspection on the sales links of the medical insurance drugs and intelligently manages the sales of the medical insurance drugs in the current cycle.

[0046] In order to better implement the above method, a medical insurance management agency management system based on big data is also proposed, which includes a characteristic medical insurance drug module, a target historical abnormal medical insurance drug module, a target abnormal data module, and an intelligent management module;

[0047] The characteristic medical insurance drug module is used to analyze the abnormal degree of medical insurance drug write-off during the drug write-off process and obtain characteristic medical insurance drugs;

[0048] The target historical abnormal medical insurance drug module is used to obtain the drug sales data of the characteristic medical insurance drugs in the current period, analyze the drug sales similarity between the characteristic medical insurance drugs and the historical abnormal medical insurance drugs, and obtain the target historical abnormal medical insurance drugs;

[0049] The target abnormal data module is used to obtain the historical abnormal data of the target historical abnormal medical insurance drugs, evaluate the abnormality of the characteristic medical insurance drugs in different sales links during the sales process in the current cycle, and obtain the target abnormal data;

[0050] The intelligent management module is used to obtain the target abnormal data of characteristic medical insurance drugs in the current cycle. Based on the target abnormal data, the medical insurance management agency conducts intelligent management of the sales of medical insurance drugs.

[0051] Furthermore, the characteristic medical insurance drug module includes a characteristic write-off abnormal value unit and a characteristic medical insurance drug unit;

[0052] A characteristic write-off abnormal value unit is used to collect medical insurance drugs according to their drug codes to obtain a medical insurance drug set, and calculate the characteristic write-off abnormal value of each medical insurance drug in the medical insurance drug set;

[0053] The characteristic medical insurance drug unit is used to analyze the drug write-off anomalies of medical insurance drugs according to the characteristic write-off anomalies to obtain characteristic medical insurance drugs.

[0054] Further, the target historical abnormal medical insurance drug module includes a drug sales approximate value unit and a target historical abnormal medical insurance drug unit;

[0055] A drug sales approximation unit is used to calculate the drug sales approximation of characteristic medical insurance drugs and historical abnormal medical insurance drugs in the database of the medical insurance management agency;

[0056] The target historical abnormal medical insurance drug unit is used to obtain the target historical abnormal medical insurance drugs of the characteristic medical insurance drugs based on the approximate sales value of the drugs.

[0057] Further, the target abnormal data module includes a link abnormal value unit and a target abnormal data unit;

[0058] Link outlier unit, used to calculate link outliers of each sales link in characteristic medical insurance drugs;

[0059] The target abnormal data unit is used to determine the abnormality of different sales links in characteristic medical insurance drugs according to the abnormal values ​​of the links, and obtain the target abnormal data of the characteristic medical insurance drugs.

[0060] Further, the intelligent management module includes an intelligent management unit;

[0061] The intelligent management unit is used to obtain each characteristic medical insurance drug in the current cycle, obtain the target abnormal data of each characteristic medical insurance drug, conduct traceability inspection on the sales link of the medical insurance drug based on the target abnormal data, and intelligently manage the sales of medical insurance drugs in the current cycle.

[0062] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention realizes intelligent management of medical insurance drugs in the sales process, analyzes the degree of abnormality in the write-off of medical insurance drugs in the write-off process, obtains characteristic medical insurance drugs with abnormal medical insurance write-off, and analyzes the similarity between the characteristic medical insurance drugs and the historical abnormal medical insurance drugs that have been detected to have problems in the sales link, thereby obtaining the sales links of the characteristic medical insurance drugs that may have abnormalities, and the medical insurance management agency optimizes and adjusts the sales process of medical insurance drugs according to the distribution of abnormal sales links. This management method not only does not require a large amount of manpower and material resources, but also can optimize the sales of medical insurance drugs according to actual conditions, greatly ensuring the authenticity of medical insurance drug transactions, and protecting the security of medical insurance funds to a certain extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 It is a method flow chart of a management system and method of a medical insurance management institution based on big data of the present invention;

[0064] Figure 2 It is a module schematic diagram of a management system and method for a medical insurance management agency based on big data according to the present invention. DETAILED DESCRIPTION

[0065] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] Example: Figure 1-Figure 2 As shown, the present invention provides a technical solution, a management method of a medical insurance management agency based on big data, the method comprising:

[0067] Step S100: Obtaining drug reimbursement data of medical insurance drugs in the current period, analyzing the degree of abnormal reimbursement of medical insurance drugs during the drug reimbursement process, and obtaining characteristic medical insurance drugs;

[0068] Wherein, step S100 includes:

[0069] Step S101: Obtaining drug reimbursement data of medical insurance drugs sold in the current period from the medical insurance management agency, the drug reimbursement data including the drug code and reimbursement amount of the medical insurance drugs;

[0070] Step S102: according to the drug codes of the medical insurance drugs, the medical insurance drugs with the same drug name and manufacturer are collected to obtain a medical insurance drug set;

[0071] Step S103: Obtain the write-off amount of each medical insurance drug in the medical insurance drug set, and calculate the characteristic data fluctuation value Q of the medical insurance drug set:

[0072]

[0073] Among them, X i is the write-off amount of the ith medical insurance drug in the medical insurance drug set; N is the total number of medical insurance drugs in the medical insurance drug set; μ is the average write-off amount of the medical insurance drugs in the medical insurance drug set;

[0074] For example, the total number N of medical insurance drugs in the medical insurance drug set is 3; the write-off amount X1 of the first medical insurance drug in the medical insurance drug set is 200; the write-off amount X2 of the second medical insurance drug in the medical insurance drug set is 220; the write-off amount X3 of the third medical insurance drug in the medical insurance drug set is 270; the average write-off amount μ of the medical insurance drugs in the medical insurance drug set is 230; calculate the characteristic data fluctuation value Q of the medical insurance drug set:

[0075]

[0076] Step S104: Calculate the characteristic write-off abnormal value of each medical insurance drug in the medical insurance drug set, where the characteristic write-off abnormal value L of the a-th medical insurance drug in the medical insurance drug set is a :

[0077]

[0078] Among them, X a is the write-off amount of the ath medical insurance drug in the medical insurance drug set;

[0079] Step S105: When the characteristic write-off abnormal value of the ath medical insurance drug is greater than the preset characteristic write-off abnormal threshold, it is determined that the ath medical insurance drug is a drug write-off abnormality in the drug write-off process, and the ath medical insurance drug is recorded as a characteristic medical insurance drug;

[0080] Step S200: Obtain historical drug sales data of historical abnormal medical insurance drugs, obtain drug sales data of characteristic medical insurance drugs in the current period, analyze the drug sales similarity between characteristic medical insurance drugs and historical abnormal medical insurance drugs, and obtain target historical abnormal medical insurance drugs;

[0081] Wherein, step S200 includes:

[0082] Step S201: Acquire historical drug sales data of historical abnormal medical insurance drugs from a database of a medical insurance management agency, wherein the historical abnormal medical insurance drugs are of the same drug type as the characteristic medical insurance drugs, and the historical drug sales data include data corresponding to various drug sales parameters of the historical abnormal medical insurance drugs;

[0083] For example, various drug sales parameters include drug sales amount, purchasing customer type, purchasing address, etc.;

[0084] Step S202: Obtain drug sales data of characteristic medical insurance drugs, where the drug sales data includes data corresponding to various drug sales parameters of the characteristic medical insurance drugs;

[0085] Step S203: Randomly select a number of historically abnormal medical insurance drugs, perform preprocessing and feature encoding on the various drug sales parameters of the several historically abnormal medical insurance drugs, obtain the feature values ​​of the various drug sales parameters, and construct a data matrix U:

[0086]

[0087] Among them, u jp is the characteristic value of the pth drug sales parameter of the jth historical abnormal medical insurance drug among several historical abnormal medical insurance drugs; u jp is the characteristic value of the pth drug sales parameter of the jth historical abnormal medical insurance drug among several historical abnormal medical insurance drugs; U 1p is the characteristic value of the pth drug sales parameter of the first historical abnormal medical insurance drug among several historical abnormal medical insurance drugs; u j1 is the characteristic value of the first drug sales parameter of the jth historical abnormal medical insurance drug among several historical abnormal medical insurance drugs; j is the total number of several historical abnormal medical insurance drugs; p is the total number of various drug sales parameters;

[0088] For example, the preprocessing process includes cleaning the collected data and dealing with missing values, duplicate values, and outliers;

[0089] Step S204: Standardize each element of the data matrix U to obtain a normalized data matrix U′, and calculate the characteristic covariance matrix C of the data matrix U′:

[0090]

[0091] Among them, U′ T is the transpose of the data matrix U′;

[0092] Step S205: Calculate the eigenvalues ​​λ and eigenvectors v of the eigencovariance matrix C, where the eigenvalues ​​λ and the eigenvectors v satisfy the equation: Cv=λv, where (C-λI)v=0, and sort the eigenvalues ​​in descending order according to their numerical values, and select the eigenvectors corresponding to the preset k eigenvalues ​​to form the projection matrix W;

[0093] Step S206: Based on the drug sales data, preprocess the data corresponding to each drug sales parameter of the characteristic medical insurance drug, and feature encode each drug sales parameter of the preprocessed characteristic medical insurance drug to obtain a characteristic sales vector group F of the characteristic medical insurance drug, and use the projection matrix to reduce the dimension of the characteristic sales vector group F to obtain the main characteristic sales vector group F of the characteristic medical insurance drug △ , where F △ =FW;

[0094] Step S207: Obtain the main characteristic sales vector group of historical abnormal medical insurance drugs, and calculate the drug sales approximation K between the characteristic medical insurance drugs and the g-th historical abnormal medical insurance drug in the database g :

[0095]

[0096] Among them, B g It is represented as the main feature sales vector group of the g-th historical abnormal medical insurance drug;

[0097] Step S208: When the drug sales approximation K g If the drug sales value is greater than the preset drug sales approximation threshold, it is determined that the drug sales status between the characteristic medical insurance drug and the g-th historical abnormal medical insurance drug is similar, and the g-th historical abnormal medical insurance drug is recorded as the target historical abnormal medical insurance drug of the characteristic medical insurance drug;

[0098] Step S300: Obtain historical abnormal data of target historical abnormal medical insurance drugs, and based on the historical abnormal data, evaluate the abnormality of different sales links of characteristic medical insurance drugs in the current cycle during the sales process to obtain target abnormal data;

[0099] Wherein, step S300 includes:

[0100] Step S301: Acquire historical abnormal data of each target historical abnormal medical insurance drug of the characteristic medical insurance drug, where the historical abnormal data is the sales link at which the target historical abnormal medical insurance drug is detected to be abnormal;

[0101] Step S302: Calculate the abnormal value of each sales link in the characteristic medical insurance drug, where the abnormal value H of the sales link of the βth item in the characteristic medical insurance drug is β :

[0102]

[0103] Among them, M sum M is the total number of historical abnormal medical insurance drugs for each target characteristic medical insurance drug; β It is represented by the total number of target historical abnormal medical insurance drugs that are detected to be abnormal in the β-th sales link;

[0104] For example, the total number of abnormal medical insurance drugs in each target history of characteristic medical insurance drugs is M sum The total number of target historical abnormal medical insurance drugs detected as abnormal in the second sales link M2 is 20;

[0105] Calculate the abnormal value H2 of the β-th sales link in the characteristic medical insurance drugs:

[0106]

[0107] For example, various sales links include drug wholesale and drug distribution;

[0108] Step S303: When the abnormal value of the β-th sales link is greater than the preset environmental abnormality threshold, it is determined that the β-th sales link in the characteristic medical insurance drug is abnormal, and the β-th sales link is recorded as the target abnormal sales link in the sales process of the characteristic medical insurance drug;

[0109] Step S304: collecting several target abnormal sales links of characteristic medical insurance drugs to obtain target abnormal data of characteristic medical insurance drugs;

[0110] Step S400: Acquire target abnormal data of characteristic medical insurance drugs in the current cycle, and based on the target abnormal data, the medical insurance management agency performs intelligent management on the sales of medical insurance drugs.

[0111] Wherein, step S400 includes:

[0112] Step S401: Acquire each characteristic medical insurance drug in the current cycle, acquire target abnormal data of each characteristic medical insurance drug, and extract target abnormal sales links of the characteristic medical insurance drug from the target abnormal data;

[0113] Step S402: Based on the target abnormal sales links of each characteristic medical insurance drug in the current cycle, the medical insurance management agency in the current cycle conducts a traceability inspection on the sales links of the medical insurance drugs, and intelligently manages the sales of the medical insurance drugs in the current cycle;

[0114] In order to better implement the above method, a medical insurance management agency management system based on big data is also proposed, which includes a characteristic medical insurance drug module, a target historical abnormal medical insurance drug module, a target abnormal data module, and an intelligent management module;

[0115] The characteristic medical insurance drug module is used to analyze the abnormal degree of medical insurance drug write-off during the drug write-off process and obtain characteristic medical insurance drugs;

[0116] The target historical abnormal medical insurance drug module is used to obtain the drug sales data of the characteristic medical insurance drugs in the current period, analyze the drug sales similarity between the characteristic medical insurance drugs and the historical abnormal medical insurance drugs, and obtain the target historical abnormal medical insurance drugs;

[0117] The target abnormal data module is used to obtain the historical abnormal data of the target historical abnormal medical insurance drugs, evaluate the abnormality of the characteristic medical insurance drugs in different sales links during the sales process in the current cycle, and obtain the target abnormal data;

[0118] The intelligent management module is used to obtain the target abnormal data of characteristic medical insurance drugs in the current cycle. Based on the target abnormal data, the medical insurance management agency conducts intelligent management of the sales of medical insurance drugs;

[0119] Among them, the characteristic medical insurance drug module includes the characteristic write-off abnormal value unit and the characteristic medical insurance drug unit;

[0120] A characteristic write-off abnormal value unit is used to collect medical insurance drugs according to their drug codes to obtain a medical insurance drug set, and calculate the characteristic write-off abnormal value of each medical insurance drug in the medical insurance drug set;

[0121] The characteristic medical insurance drug unit is used to analyze the abnormality of drug write-off of medical insurance drugs according to the abnormal value of characteristic write-off, and obtain the characteristic medical insurance drugs;

[0122] Among them, the target historical abnormal medical insurance drug module includes the drug sales approximate value unit and the target historical abnormal medical insurance drug unit;

[0123] A drug sales approximation unit is used to calculate the drug sales approximation of characteristic medical insurance drugs and historical abnormal medical insurance drugs in the database of the medical insurance management agency;

[0124] A target historical abnormal medical insurance drug unit is used to obtain target historical abnormal medical insurance drugs of characteristic medical insurance drugs based on the approximate sales value of the drugs;

[0125] Among them, the target abnormal data module includes a link abnormal value unit and a target abnormal data unit;

[0126] Link outlier unit, used to calculate link outliers of each sales link in characteristic medical insurance drugs;

[0127] The target abnormal data unit is used to determine the abnormality of different sales links of characteristic medical insurance drugs according to the abnormal values ​​of the links, and obtain the target abnormal data of the characteristic medical insurance drugs;

[0128] Wherein, the intelligent management module includes an intelligent management unit;

[0129] The intelligent management unit is used to obtain each characteristic medical insurance drug in the current cycle, obtain the target abnormal data of each characteristic medical insurance drug, conduct traceability inspection on the sales link of the medical insurance drug based on the target abnormal data, and intelligently manage the sales of medical insurance drugs in the current cycle.

[0130] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A management method for a medical insurance management agency based on big data, characterized in that: The method comprises: Step S100: Obtaining drug reimbursement data of medical insurance drugs in the current period, analyzing the degree of abnormal reimbursement of medical insurance drugs during the drug reimbursement process, and obtaining characteristic medical insurance drugs; Step S200: Obtain historical drug sales data of historical abnormal medical insurance drugs, obtain drug sales data of characteristic medical insurance drugs in the current period, analyze the drug sales similarity between characteristic medical insurance drugs and historical abnormal medical insurance drugs, and obtain target historical abnormal medical insurance drugs; Step S300: Acquire the historical abnormal data of the target historical abnormal medical insurance drug, and based on the historical abnormal data, evaluate the abnormality of different sales links of the characteristic medical insurance drug in the current cycle during the sales process to obtain the target abnormal data; Step S400: Acquire target abnormal data of characteristic medical insurance drugs in the current cycle, and based on the target abnormal data, the medical insurance management agency performs intelligent management on the sales of medical insurance drugs.

2. According to the big data-based medical insurance management agency management method of claim 1, it is characterized in that: The step S100 includes: Step S101: obtaining drug reimbursement data of medical insurance drugs sold in the current period from the medical insurance management agency, wherein the drug reimbursement data includes the drug code and reimbursement amount of the medical insurance drugs; Step S102: according to the drug codes of the medical insurance drugs, the medical insurance drugs with the same drug name and manufacturer are collected to obtain a medical insurance drug set; Step S103: Obtain the write-off amount of each medical insurance drug in the medical insurance drug set, and calculate the characteristic data fluctuation value Q of the medical insurance drug set: Among them, X i is the write-off amount of the ith medical insurance drug in the medical insurance drug set; N is the total number of medical insurance drugs in the medical insurance drug set; μ is the average write-off amount of the medical insurance drugs in the medical insurance drug set; Step S104: Calculate the characteristic write-off abnormal value of each medical insurance drug in the medical insurance drug set, wherein the characteristic write-off abnormal value L of the a-th medical insurance drug in the medical insurance drug set is a : Among them, X a is the write-off amount of the ath medical insurance drug in the medical insurance drug set; Step S105: When the characteristic write-off anomaly value of the ath medical insurance drug is greater than a preset characteristic write-off anomaly threshold, it is determined that the ath medical insurance drug is a drug write-off anomaly during the drug write-off process, and the ath medical insurance drug is recorded as a characteristic medical insurance drug.

3. According to the big data-based medical insurance management agency management method of claim 2, it is characterized in that: The step S200 includes: Step S201: Acquire historical drug sales data of historical abnormal medical insurance drugs from a database of a medical insurance management agency, wherein the historical abnormal medical insurance drugs are of the same drug type as the characteristic medical insurance drugs, and the historical drug sales data include data corresponding to various drug sales parameters of the historical abnormal medical insurance drugs; Step S202: obtaining drug sales data of the characteristic medical insurance drug, wherein the drug sales data includes data corresponding to various drug sales parameters of the characteristic medical insurance drug; Step S203: randomly select a number of historically abnormal medical insurance drugs, perform preprocessing and feature encoding on the various drug sales parameters of the several historically abnormal medical insurance drugs, obtain the feature values ​​of the various drug sales parameters, and construct a data matrix U: Among them, u jp is the characteristic value of the pth drug sales parameter of the jth historical abnormal medical insurance drug among the several historical abnormal medical insurance drugs; jp is the characteristic value of the pth drug sales parameter of the jth historical abnormal medical insurance drug among the several historical abnormal medical insurance drugs; U 1p is the characteristic value of the pth drug sales parameter of the first historical abnormal medical insurance drug among the several historical abnormal medical insurance drugs; j1 is the characteristic value of the first drug sales parameter of the jth historical abnormal medical insurance drug among the several historical abnormal medical insurance drugs; j is the total number of the several historical abnormal medical insurance drugs; p is the total number of various drug sales parameters; Step S204: Standardize each element of the data matrix U to obtain a normalized data matrix U′, and calculate the characteristic covariance matrix C of the data matrix U′: Among them, U′ T is the transpose of the data matrix U′; Step S205: Calculate the eigenvalue λ and eigenvector v of the eigencovariance matrix C, wherein the eigenvalue λ and the eigenvector v satisfy the equation: Cv=λv, wherein (C-λI)v=0, and arrange the eigenvalues ​​in descending order according to their numerical values, and select the eigenvectors corresponding to the preset k eigenvalues ​​to form a projection matrix W; Step S206: Based on the drug sales data, preprocess the data corresponding to each drug sales parameter of the characteristic medical insurance drug, and feature encode each drug sales parameter of the preprocessed characteristic medical insurance drug to obtain a characteristic sales vector group F of the characteristic medical insurance drug, and use the projection matrix to reduce the dimension of the characteristic sales vector group F to obtain the main characteristic sales vector group F of the characteristic medical insurance drug. △ , where F △ =FW; Step S207: Obtain the main characteristic sales vector group of the historical abnormal medical insurance drug, and calculate the drug sales approximation K between the characteristic medical insurance drug and the g-th historical abnormal medical insurance drug in the database g : Among them, B g It is represented as the main feature sales vector group of the g-th historical abnormal medical insurance drug; Step S208: When the drug sales approximation K g If the drug sales value is greater than a preset drug sales approximation threshold, it is determined that the drug sales conditions between the characteristic medical insurance drug and the g-th historical abnormal medical insurance drug are similar, and the g-th historical abnormal medical insurance drug is recorded as the target historical abnormal medical insurance drug of the characteristic medical insurance drug.

4. According to the big data-based medical insurance management agency management method of claim 3, it is characterized in that: The step S300 includes: Step S301: acquiring historical abnormal data of each target historical abnormal medical insurance drug of the characteristic medical insurance drug, wherein the historical abnormal data is the sales link at which the target historical abnormal medical insurance drug is detected to be abnormal; Step S302: Calculate the abnormal value of each sales link in the characteristic medical insurance drug, where the abnormal value H of the sales link of the βth item in the characteristic medical insurance drug is β : Among them, M sum M is the total number of each target historical abnormal medical insurance drug of the characteristic medical insurance drug; β It is represented by the total number of target historical abnormal medical insurance drugs detected to be abnormal in the β-th sales link; Step S303: When the abnormal value of the β-th sales link is greater than the preset environmental abnormality threshold, it is determined that the β-th sales link in the characteristic medical insurance drug is abnormal, and the β-th sales link is recorded as the target abnormal sales link in the sales process of the characteristic medical insurance drug; Step S304: Gathering several target abnormal sales links of the characteristic medical insurance drugs to obtain target abnormal data of the characteristic medical insurance drugs.

5. A method for managing a medical insurance management institution based on big data according to claim 4, characterized in that: The step S400 includes: Step S401: Acquire each characteristic medical insurance drug in the current cycle, acquire target abnormal data of each characteristic medical insurance drug, and extract target abnormal sales links of the characteristic medical insurance drug from the target abnormal data; Step S402: Based on the target abnormal sales links of each characteristic medical insurance drug in the current cycle, the medical insurance management agency in the current cycle conducts a traceability inspection on the sales links of the medical insurance drugs and intelligently manages the sales of the medical insurance drugs in the current cycle.

6. A medical insurance management agency management system based on big data, used to execute a medical insurance management agency management method based on big data as described in any one of claims 1 to 5, characterized in that: The system includes a characteristic medical insurance drug module, a target historical abnormal medical insurance drug module, a target abnormal data module, and an intelligent management module; The characteristic medical insurance drug module is used to analyze the abnormality of the medical insurance drug write-off during the drug write-off process to obtain characteristic medical insurance drugs; The target historical abnormal medical insurance drug module is used to obtain drug sales data of characteristic medical insurance drugs in the current period, analyze the drug sales similarity between characteristic medical insurance drugs and historical abnormal medical insurance drugs, and obtain target historical abnormal medical insurance drugs; The target abnormal data module is used to obtain the historical abnormal data of the target historical abnormal medical insurance drugs, evaluate the abnormality of different sales links of the characteristic medical insurance drugs in the current cycle during the sales process, and obtain the target abnormal data; The intelligent management module is used to obtain target abnormal data of characteristic medical insurance drugs in the current cycle. Based on the target abnormal data, the medical insurance management agency performs intelligent management on the sales of medical insurance drugs.

7. A medical insurance management agency management system based on big data according to claim 6, characterized in that: The characteristic medical insurance drug module includes a characteristic write-off abnormal value unit and a characteristic medical insurance drug unit; The characteristic write-off abnormal value unit is used to collect medical insurance drugs according to the drug codes of the medical insurance drugs to obtain a medical insurance drug set, and calculate the characteristic write-off abnormal value of each medical insurance drug in the medical insurance drug set; The characteristic medical insurance drug unit is used to analyze the medical insurance drug write-off anomalies according to the characteristic write-off anomaly values ​​to obtain characteristic medical insurance drugs.

8. The medical insurance management agency management system based on big data according to claim 6, characterized in that: The target historical abnormal medical insurance drug module includes a drug sales approximate value unit and a target historical abnormal medical insurance drug unit; The drug sales approximation unit is used to calculate the drug sales approximation of the characteristic medical insurance drugs and the historical abnormal medical insurance drugs in the database of the medical insurance management agency; The target historical abnormal medical insurance drug unit is used to obtain the target historical abnormal medical insurance drug of the characteristic medical insurance drug according to the approximate drug sales value.

9. The medical insurance management agency management system based on big data according to claim 6, characterized in that: The target abnormal data module includes a link abnormal value unit and a target abnormal data unit; The link abnormal value unit is used to calculate the link abnormal values ​​of each sales link in the characteristic medical insurance drug; The target abnormal data unit is used to determine the abnormality of different sales links of the characteristic medical insurance drugs according to the link abnormal values, so as to obtain the target abnormal data of the characteristic medical insurance drugs.

10. The medical insurance management institution management system based on big data according to claim 6, characterized in that: The intelligent management module includes an intelligent management unit; The intelligent management unit is used to obtain each characteristic medical insurance drug in the current cycle, obtain the target abnormal data of each characteristic medical insurance drug, conduct a traceability inspection on the sales link of the medical insurance drug based on the target abnormal data, and intelligently manage the sales of the medical insurance drugs in the current cycle.

Images